We have been awarded $1M funding from the Chan Zuckerberg Initiative (CZI) to develop an AI model of the maternal brain, offering unprecedented insights into how the brain changes during pregnancy and motherhood.
By leveraging multimodal geometric deep learning, we will create dynamic 3D models (also called "atlases" or "templates") of the maternal brain that adapt based on hormone levels, physiology, and demographics. These models will identify patterns of brain evolution, uncover population-level differences, and predict postpartum conditions such as depression. We will dedicate resources to ensure that these models are explainable and fair, accurately representing diverse populations.
At the heart of this work lies the Bowers WBHI Maternal Brain Project (MBP) dataset, a first-of-its-kind resource mapping neuroanatomical changes from preconception through two years postpartum, for a diverse population of first-time mothers in the U.S. and Spain. With its multimodal data—including cognitive assessments, reproductive health, and proteomics—the MBP provides the foundation for our transformative AI effort. Together, these data-driven insights and AI advancements aim to revolutionize our understanding of maternal mental health, a historically under-researched yet urgent public health priority.
This project will be carried forward through the Bowers WBHI AI Core, with leadership team comprising Nina Miolane, Susana Carmona, Emily Jacobs, and Magdalena Martinez Garcia, in collaboration with the Chan Zuckerberg Initiative. Together, we are committed to advancing science toward a more inclusive, equitable, and healthier future.
Picture credits: Susana Carmona's Book Cover. Neuromaternal.